ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 12. Vol. 31. 2025

DOI: 10.17587/it.31.637-648

P. M. Niang, Graduate Student, V. G. Sidorenko, Dr. of Tech. Sc., Professor, Department of Information Management and Protection,
Russian University of Transport RUT (MIIT) Moscow, 127994, Russian Federation

Machine Learning-Based Defense Against Adversarial Attacks in Intrusion Detection Systems

Received on 04.07.2025
Accepted on 30.07.2025

In this paper, common types of adversarial attacks (DTA, FGSM, and BIM) are used to generate adversarial samples to test the vulnerability of IDS using the UNSW-NB15 dataset. Then, basic defense mechanisms are developed, including adversarial pattern detection and filtering. Experiments are conducted on Random Forest (RF) and Logistic Regression (LR) machine learning classifier.
Keywords: intrusion detection system, machine learning, adversarial samples, random forest, logistic regression

P. 637-648

Full text on eLIBRARY

References

1. Niang P. M., Sidorenko V. G. Choosing the machine learning algorithm for detecting intrusions into IoT, Dependability, 2024, vol. 24, no 3, p. 44—51, DOI: 10.21683/1729-2646-2024-24-3-44-51.
2. Malik N. P., Sidorenko V. G. Application of Multi classification for Detecting Intrusions in IoT and Their Type Recognizing, 2024 International Conference" Quality Management, Transport and Information Security, Information Technologies"(QM&TIS&IT), IEEE, 2024, pp. 78—83, DOI: 10.1109/QMTISIT63393.2024.10762926.
3. Moustafa N., Slay J. UNSW-NB15: À comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set), 2015 Military Communications and Information Systems Conference (MilCIS), Nov. 2015, pp. 1—6, DOI: 10.1109/MilCIS.2015.7348942.
4. Niang P. M. Analysis of data sets for research of computer network vulnerabilities, III International Scientific and Practical Conference "Intelligent Transport Systems" (May 30, 2024), Moscow, Pero Publishing House, 2024, pp. 699—709.
5. Haroon M. Sh., Husnain M. A. Adversarial Training Against Adversarial Attacks for Machine Learning-Based Intrusion Detection Systems, Computers, Materials & Continua, 2022, vol. 73, no. 2.
6. Ilyushin E., Namiot D., Chizhov I. Attacks on machine learning systems-common problems and methods, International Journal of Open Information Technologies, 2022, vol. 10, no. 3, p. 17—22, available at: http://injoit.org/index.php/j1/article/view/1276.
7. Potapov A. K., Sidorenko V. G. Vulnerabilities of Artificial Intelligence Systems. In: 2024 International Conference" Quality Management, Transport and Information Security, Information Technologies"(QM&TIS&IT). IEEE, 2024, pp. 84—87, DOI:10.1109/QMTISIT63393.2024.10762915.
8. Yang L., El Rajab M., Shami À . Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysis, IEEE Transactions on Network and Service Management, 2024.
9. Kulagin M. A., Loginova L. N., Niang P. M., Sidorenko V. G. Developing skills in using machine learning algorithms among information security specialists, Informatization of education and science, 2025, no. 1 (65), pp. 56—65.

To the contents